Connor Shorten - Research Scientist, Weaviate - ChatGPT, LLMs, Form vs Meaning

Topics:00:00 Intro01:54 Things Connor learnt in the past year that changed his perception of Vector Search02:42 Is search becoming conversational?05:46 Connor asks Dmitry: How Large Language Models will change Search?08:39 Vector Search Pyramid09:53 Large models, data, Form vs Meaning and octopus underneath the ocean13:25 Examples of getting help from ChatGPT and how it compares to web search today18:32 Classical search engines with URLs for verification vs ChatGPT-style answers20:15 Hybrid search: keywords + semantic retrieval23:12 Connor asks Dmitry about his experience with sparse retrieval28:08 SPLADE vectors34:10 OOD-DiskANN: handling the out-of-distribution queries, and nuances of sparse vs dense indexing and search39:54 Ways to debug a query case in dense retrieval (spoiler: it is a challenge!)44:47 Intricacies of teaching ML models to understand your data and re-vectorization49:23 Local IDF vs global IDF and how dense search can approach this issue54:00 Realtime index59:01 Natural language to SQL1:04:47 Turning text into a causal DAG1:10:41 Engineering and Research as two highly intelligent disciplines1:18:34 Podcast search1:25:24 Ref2Vec for recommender systems1:29:48 AnnouncementsFor Show Notes, please check out the YouTube episode below.This episode on YouTube: https://www.youtube.com/watch?v=2Q-7taLZ374Podcast design: Saurabh Rai: https://twitter.com/srvbhr